arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11824cs.CV
收藏

从驾驶员视角图像中检测无标志物理道路事件

Detecting Unsigned Physical Road Incidents from Driver-View Images

Wageningen University(瓦赫宁根大学);University of Melbourne(墨尔本大学)

Alex Levering, Martin Tomko, Devis Tuia, Kourosh Khoshelham

摘要:

道路安全至关重要,尤其是在自动驾驶汽车的情况下。一个关键的需求是及早有效地发现和沟通破坏性事件。在本文中,我们提出了一个系统的基础上,现成的深神经网络架构,能够检测和识别类型的无符号(非标牌,如交通标志),物理(图像中可见)的道路事故。我们为未签名的物理事件开发了一个分类,以提供一种组织和分组相关事件的方法。在选择了八种目标类型的事件后,我们收集了从公开的网络资源中收集的一万二千张图像的数据集。我们随后微调卷积神经网络,以识别八种类型的道路事故。所提出的模型是能够识别事件具有较高的准确率(高于90%)。我们进一步表明,虽然我们的系统概括以及跨空间环境的训练分类器在英国的地理分层数据(准确率超过90%),翻译到视觉上不太相似的环境需要空间分布的数据汇集。注:这是IEEE智能车辆学报(T-IV;印刷中)接受的工作的预印本。该文件目前正在制作中,DOI链接将很快添加。

英文摘要:

Safety on roads is of uttermost importance, especially in the context of autonomous vehicles. A critical need is to detect and communicate disruptive incidents early and effectively. In this paper we propose a system based on an off-the-shelf deep neural network architecture that is able to detect and recognize types of unsigned (non-placarded, such as traffic signs), physical (visible in images) road incidents. We develop a taxonomy for unsigned physical incidents to provide a means of organizing and grouping related incidents. After selecting eight target types of incidents, we collect a dataset of twelve thousand images gathered from publicly-available web sources. We subsequently fine-tune a convolutional neural network to recognize the eight types of road incidents. The proposed model is able to recognize incidents with a high level of accuracy (higher than 90%). We further show that while our system generalizes well across spatial context by training a classifier on geostratified data in the United Kingdom (with an accuracy of over 90%), the translation to visually less similar environments requires spatially distributed data collection. Note: this is a pre-print version of work accepted in IEEE Transactions on Intelligent Vehicles (T-IV;in press). The paper is currently in production, and the DOI link will be added soon.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑